← 返回 Skills 市场
68
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install talonforge-safety
功能描述
Automatically configures trust levels, non-negotiable safety rules, prompt injection defenses, and approval workflows for secure AI interactions.
安全使用建议
This skill looks like a genuine safety-rails template, but it contains several gaps you should resolve before installing: (1) Verify the npm packages it asks you to install (ai-sentinel, skill-guard) — inspect their source, maintainers, and npm page; don't run npx blindly. (2) Ask the author how the agent is expected to access email/messaging channels and where any tokens are stored; prefer explicit, minimal credential requirements and short-lived tokens. (3) Confirm where installed tooling will be placed and what permissions it will have. (4) Prefer an install manifest from a known origin (GitHub release or vetted registry) rather than ad-hoc npx commands. (5) If you plan to allow the agent to read emails/files, limit access scope and test in a sandbox first. If you cannot verify the third-party packages or the homepage/author identity, treat this as higher risk and do not install.
功能分析
Type: OpenClaw Skill
Name: talonforge-safety
Version: 1.0.0
The bundle provides a framework for AI safety guardrails, including a multi-level trust system and defensive instructions designed to mitigate prompt injection and unauthorized autonomous actions. The SKILL.md file contains purely instructional content that constrains the agent's behavior (e.g., prohibiting financial transactions and treating inbound email as untrusted), and it references the installation of safety-oriented utilities (ai-sentinel, skill-guard) via the platform's package manager. No malicious logic, data exfiltration, or obfuscation was detected.
能力评估
Purpose & Capability
The skill claims to set up safety rails that include reading files, messages and emails and integrating with a 'verified messaging channel', but the package metadata declares no required env vars, credentials, or config paths. That mismatch (ability to read/act on messages + no declared access requirements) is inconsistent and unexplained.
Instruction Scope
SKILL.md instructs the agent to collect user answers (risk tolerance, hard rules, verified channel) and to generate configuration, but it also prescribes behaviors that imply reading emails/messages and preventing/handling prompt-injection. The instructions also tell the user/agent to run npx install commands to add third-party components — this expands scope beyond the simple prose and is vague about what those components will do or what data they will access.
Install Mechanism
Although there is no formal install spec, the SKILL.md tells the operator to run 'npx clawhub@latest install ai-sentinel' and 'npx clawhub@latest install skill-guard'. That implies installing public npm packages at runtime via npx (moderate risk): those packages are external, their provenance and behavior are unknown, and installing them will persist code on disk/executable context without a vetted install manifest.
Credentials
The skill will likely need access to messaging channel credentials and possibly mailbox access to enforce email rules, but requires.env and primary credential fields are empty. Asking for a 'verified messaging channel' without declaring how tokens/credentials are supplied or stored is a proportionality mismatch and a potential blind spot for credential handling.
Persistence & Privilege
always is false and the skill is user-invocable (normal). However, the SKILL.md's recommended npx installs imply adding persistent tools (ai-sentinel, skill-guard) to the environment, which increases long-term privilege surface even though the skill itself does not request always:true or system-wide config changes.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install talonforge-safety - 安装完成后，直接呼叫该 Skill 的名称或使用
/talonforge-safety触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
First release. Bilingual safety guardrails from TalonForge.
元数据
常见问题
TalonForge Safety Rails (EN/AR) 是什么？
Automatically configures trust levels, non-negotiable safety rules, prompt injection defenses, and approval workflows for secure AI interactions. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 68 次。
如何安装 TalonForge Safety Rails (EN/AR)？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install talonforge-safety」即可一键安装，无需额外配置。
TalonForge Safety Rails (EN/AR) 是免费的吗？
是的，TalonForge Safety Rails (EN/AR) 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
TalonForge Safety Rails (EN/AR) 支持哪些平台？
TalonForge Safety Rails (EN/AR) 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 TalonForge Safety Rails (EN/AR)？
由 zinou（@casperzinou）开发并维护，当前版本 v1.0.0。
推荐 Skills